With the rapid development of wireless communication technology, security issues in wireless networks have become increasingly serious, leading to the emergence of Radio Frequency Fingerprint (RFF) as an important device authentication technology. RFF identifies and verifies device identities by analyzing the wireless signals emitted by devices. However, the inherent complexity and non-Euclidean characteristics of signal features pose significant challenges for traditional machine learning and deep learning approaches in RFF. Graph Neural Networks (GNNs) uniquely address these limitations by explicitly modeling signal relationships through graph-structured representations, enabling effective capture of high-order interactions and dynamic adaptation to signal variations through message passing mechanisms. To this end, this paper proposes an efficient Attention-Enhanced Graph Convolutional Network (EAGCN) for RFF identification. The network employs an Adaptive Visibility Graph (AVG) Generator and Efficient Channel Attention (ECA) mechanisms to enhance the capture of key features, and combines these with DenseGCN graph convolution layers to better capture spatial correlations. Additionally, we introduce Graph Double Implicit Regularization (GDIR) into the network to further improve its generalization ability in few-shot transfer tasks. Experimental results on a multi-transmitter multi-receiver WiFi dataset show that GDIR-EAGCN significantly outperforms existing methods, particularly excelling in transfer learning tasks. Furthermore, an ablation study was conducted to validate the contribution of each component to the overall performance.

Laser-based Simultaneous Localization and Mapping (SLAM) is fundamental to autonomous navigation systems. However, conventional frameworks such as Lightweight and Ground-Optimized LiDAR Odometry and Mapping (LeGO-LOAM) face challenges in geometric segmentation robustness, feature extraction accuracy, and loop closure reliability, especially in complex and dynamic environments. To overcome these limitations, this paper proposes LeGO-LOAM-RAS, a semantic-aware, graph-based LiDAR SLAM framework that integrates RandLA-Net for multi-class semantic segmentation, a depth-guided AFE strategy, and a semantic-contextual loop closure mechanism. In the proposed system, RandLA-Net replaces traditional geometry-based segmentation with a deep learning approach, enabling fine-grained scene understanding and the effective discrimination of objects such as roads, vehicles, and buildings. This enhances both local contextual awareness and global structural representation. The AFE module dynamically adjusts neighborhood configurations and angular resolutions based on depth cues, employing depth-error-based noise suppression and curvature refinement to improve the reliability of planar and edge features. For loop closure, a semantic-contextual descriptor is constructed by fusing geometric features with semantic histograms in a polar grid representation, introducing joint geometric-semantic constraints. This design improves loop closure robustness by mitigating ambiguity in perceptually similar environments and suppressing the impact of dynamic elements. Extensive evaluations on publicly available benchmark datasets validate the effectiveness of LeGO-LOAM-RAS, demonstrating substantial improvements in localization accuracy and overall system robustness compared to state-of-the-art methods.

In recent years, semantic segmentation of large-scale point clouds has garnered significant attention due to its critical role in 3D scene understanding. However, the inherent complexity and uneven distribution of large-scale point clouds, coupled with substantial inter-class similarity, significantly hinder the discriminative power of existing segmentation approaches. RandLA-Net has shown strong capabilities in directly inferring semantic information. Building upon this foundation, we proposed three redesigned modules to improve the accuracy of point cloud segmentation: a Local Contextual Feature (LCF) module, a Global Contextual Feature (GCF) module and, a Contextual Feature Enhancement (CFE) module. The LCF module preserves the local spatial encoding unit and introduces an improved dual attention mechanism that independently computes geometric and feature-based attention scores. This facilitates more effective local feature aggregation and overcomes the segmentation artifacts caused by the difficulty in distinguishing similar classes. To complement local representations, the GCF module is integrated to capture scene-level semantics across all 3D points by using the spatial position volume ratio, thereby addressing feature extraction from both local and global perspectives. The CFE module is designed as a plug-and-play component, which enhances feature representations by integrating richer contextual cues from both explicit 3D geometry and implicit feature spaces, along with global bilinear interactions. Comprehensive experiments on the S3DIS (indoor) and Semantic3D (outdoor) datasets show that our method attains Overall Accuracy (OA) scores of 89.8% and 95.3%, and mean Intersection over Union (mIoU) scores of 73.3% and 78.0%, respectively, outperforming existing methods and providing new perspectives for large-scale point cloud semantic segmentation across diverse environments.

Radio Frequency Fingerprint (RFF) identification plays a critical role in physical-layer security by enabling the identification of wireless devices. Recent advances have leveraged deep learning (DL) to enhance performance and robustness. However, existing DL-based RFF identification methods rely heavily on large-scale labeled signal datasets, making data annotation costly and challenging, particularly in complex electromagnetic environments. To address this limitation, we propose a self-supervised RFF identification method based on Time-Frequency Contrastive Learning (TFCL), designed to operate on unlabeled signal samples. The framework consists of two key modules: (1) a time-frequency contrastive self-supervised learning module, which constructs robust RFF feature embeddings from unlabeled signals, and (2) a CutMix-based regularized finetuning module, which enhances robustness through regularized training. Moreover, we introduce parameter freezing integrated with CutMix to adapt to diverse downstream scenarios. Extensive experiments demonstrate that the proposed TFCL-based method achieves superior feature embedding quality and identification accuracy compared to four competitive baselines, highlighting its effectiveness in real-world applications.

With the growing adoption of Internet of Things (IoT) devices, ensuring the security of wireless communications has become increasingly critical. Radio frequency fingerprint identification (RFFI) has shown promise in this regard due to its capability of uniquely identifying devices. Although deep learning (DL) approaches have significantly improved RFFI performance, they typically rely on large-scale centralized data. This poses challenges in terms of privacy preservation and heterogeneous data distributions. To address the performance degradation caused by non-independent and identically distributed (non-IID) data in cross-receiver scenarios, this paper proposes a feature alignment strategy based on federated learning (FL) for RFFI. In such scenarios, due to differences in receiver hardware characteristics, deployment locations, and channel conditions, the signals captured by different receivers often exhibit distribution shifts, resulting in misaligned feature spaces across clients. The proposed method guides each client to learn aligned intermediate feature representations during local training, effectively mitigating the resulting adverse impact on model generalization. Experiments conducted on a real-world RF dataset demonstrate that the proposed method achieves higher identification accuracy and improved stability compared with representative federated baselines, including FedAvg and FedProx. The highest identification accuracy reaches 90.83%, and the performance gains are accompanied by generally reduced variance across different client configurations, highlighting the robustness and generalization capability of the proposed approach in heterogeneous wireless environments.

Specific Emitter Identification (SEI) leverages unique hardware-induced Radio Frequency Fingerprints (RFFs) for secure physical-layer authentication. However, under cross-receiver scenarios where training and testing data exhibit hardware-induced distribution shifts, deep learning models are prone to shortcut learning. In such cases, networks inadvertently exploit spurious, receiver-specific artifacts as ”shortcuts” for identification rather than extracting the genuine, intrinsic fingerprints of the transmitter. To overcome this challenge, we propose a robust multi-task learning framework, termed MTL-SEI. This framework synergizes spectrum-based feature extraction with receiver-invariant adversarial training and channel-aware auxiliary supervision. Specifically, a gradient reversal layer (GRL) is employed to suppress receiver-dependent features, while an equalization-state prediction task provides semantic guidance to disentangle channel-induced distortions. Furthermore, an uncertainty-guided task weighting mechanism is introduced to dynamically balance the multiple optimization objectives based on predictive variance. Evaluations conducted on the ManySig dataset under a rigorous receiver-disjoint protocol demonstrate the superior generalization capability of MTL-SEI. Notably, our method achieves a transmitter identification accuracy of 88.50% —representing a 37.7% improvement over the 1D-CNN baseline—and yields an average performance gain of over 6.92% compared to state-of-the-art domain generalization methods. These results validate the effectiveness of the proposed feature disentanglement mechanism in mitigating receiver-induced biases.

In cognitive heterogeneous networks, multiple secondary transmitters (STs) co-exist with primary users (PUs) on the same frequency band channel through spectrum sensing. Due to inaccurate sensing of whether the channel is occupied, STs can cause interference to PUs, thereby affecting the transmission performance of PUs. This paper proposes a constrained deep reinforcement learning-based joint adaptive modulation coding and power selection (CDRL-JAMCPS) algorithm. The proposed CDRL-JAMCPS learns the interference patterns of STs to PUs through interaction with the environment and selects the modulation coding scheme and transmit power for future frames of PUs based on the learned patterns, aiming to maximize the transmission rate while reducing energy consumption. Furthermore, addressing the issue where existing optimization algorithms solely consider network transmission rates while neglecting data transmission quality, this paper proposes a reward function in Lagrangian form based on frame error rate (FER) constraints. By optimizing this reward function in its dual domain, the problem of poor data transmission quality is resolved. The simulation results demonstrate that the proposed algorithm achieves better transmission performance compared to other reinforcement learning algorithms in environments where signal interference is difficult to perceive. Meanwhile, compared to algorithms that do not consider transmission quality, our algorithm exhibits significant advantages in meeting FER requirements and improving data transmission quality.

As the global population continues to age and technologies such as the Internet of Things (IoT) and edge computing advance rapidly, indoor human activity recognition (HAR) based on Wi-Fi channel state information (CSI) has gained significant research attention. However, the high computational complexity of existing HAR methods limits their deployment on resource-constrained devices. To address this challenge, we propose a lightweight HAR method using branch decision lightweight two-stream convolution-augmented transformer (BLTHAT) model, which integrates depthwise separable convolutions (DSC) and an improved framework structure to enhance computational efficiency. Additionally, we introduce the branch fusion network (BFN), a decision-making module designed to optimize feature processing and improve model robustness. Further enhancements in attention mechanisms and regularization strategies contribute to reducing complexity while maintaining high recognition accuracy. Comprehensive experiments were conducted on a multi-label dataset. The results demonstrate that our proposed HAR method achieves high computational efficiency with minimal complexity, making it well-suited for IoT applications. Ablation studies further confirm that the multi-branch structure of the BFN module enhances feature extraction without significantly increasing computational overhead.

Automatic modulation classification (AMC) is a fundamental technology for identifying modulation types in non-cooperative communication systems. It plays a crucial role in various applications, including spectrum monitoring, cognitive radio, and signal intelligence. Recently, deep learning (DL) based AMC methods have achieved remarkable classification accuracy. However, their practical deployment in resource-constrained edge devices remains challenging due to their high computational complexity and excessive model size. To address this limitation, we propose an ultra-lightweight AMC method based on filter pruning via geometric median (FPGM). The key idea is to leverage the geometric median as a robustness-driven filter selection criterion, effectively eliminating redundant convolutional kernels while preserving essential model representations. Specifically, we first determine the geometric median of the filters in each layer, which effectively represents the distribution of filters within that layer. Then, filters near the geometric median are identified and filtered out through the characteristics of the geometric median. Finally, the performance degradation of the model caused by the removal of filters can be restored through fine-tuning. Experimental results demonstrate that the proposed AMC method achieves a 99% reduction in model size while limiting the classification accuracy drop to merely 1.61%, significantly outperforming other lightweight AMC techniques. These results highlight the feasibility of deploying the proposed AMC model on edge Internet of Things (IoT) devices, enabling efficient real-time modulation classification with minimal computational overhead.

Accurate streamflow (SF) forecasting is crucial for effective water-resource management amid global climate change. Traditional ensemble SF-forecasting methods, relying on historical data and watershed characteristics, often produce uncertainties in their input, structure, and parameters, reducing their forecasting accuracy. This study introduces a variance-combined bias-correction (VCB) method, integrated with Internet of Things (IoT) technology to improve ensemble SF forecasts’ accuracy and responsiveness. The VCB method significantly improves the SF-forecasting performance by incorporating variance information from ensemble forecasts along with the ensemble mean. We apply the method to the Shiquan Reservoir in China’s Han River basin, and the results show that the VCB method outperforms the Bayesian joint probability (BJP) method, achieving an increases of 8.8% in the Nash-Sutcliffe efficiency (NSE), 0.7% in the Pearson correlation coefficient (PCC), 2.1% in the qualified rate (QR), and a 7.2% reduction in the mean absolute percentage error (MAPE). Furthermore, IoT technology integration improves method inputs’ accuracy and timeliness, showing the strongest performance during extreme weather events. Thus, by improving uncertainty management and forecasting accuracy, the IoT-integrated VCB method provides more effective support for water-resource management. Future research should apply this approach to diverse hydrological contexts and explore deeper integration with machine-learning techniques.

Specific emitter identification (SEI) is a passive physical layer authentication technology that mines subtle hardware differences between emitters to identify devices. However, traditional deep learning-based SEI is trained for scenarios with massive signal samples and performs poorly in sample-limited scenarios. To solve this problem, we proposed a robust few-shot SEI (FS-SEI) method using dual-level data augmentation, consisting of phase shift position prediction and manifold cutMix (P3MC). We perform data augmentation in both the sample space and the feature space to accelerate the complex valued time series lightweight adaptive network (CV-TSLANet) to learn robust features and use machine learning to identify ADS-B emitters. Our experimental results show that the performance of our proposed FS-SEI method reaches 90% when the number of samples per category is 30. We have open-sourced the proposed FS-SEI method at https://github.com/IcedWatermelonJuice/P3MC.

With the development of the Industrial Internet of Things (IIoT), more frequent attacks occur to intrude IIoT devices. A reasonably designed intrusion detection method can effectively guarantee the security of IIoT. Over the past decade, different methods of intrusion detection based on deep learning (DL) have been proposed, which helps intrusion detection keep evolving and become more robust. However, these previous researches usually require the participation of a large number of experts, and gradually become invalid with the continuous development of intrusion methods. The limited compute capability of IIoT devices also greatly hinder the deployment of overly complex DL models. To address these challenges, this paper proposes a lightweight semi-supervised learning (LSSL) method based on consistency regularization for intrusion detection. Our proposed method enhances the detection performance by using unlabeled traffic data for consistency training. Besides, we adopt separable convolutions for efficient feature extraction. Experimental results on two widely-used benchmark datasets show that the detection performance of our model is significantly improved by the consistency training, and it can effectively detect various attacks in complex networks.